Skip to content

🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev

Style adjustments by flake8

Karim shoair97fecc9d5fe6
diff --git a/.flake8 b/.flake8
index 5a89b58..fae58af 100644
--- a/.flake8
+++ b/.flake8
@@ -1,3 +1,3 @@
[flake8]
-ignore = E501 # line too long
-exclude = .git,__pycache__,docs,.github,build,dist
\ No newline at end of file
+ignore = E501, F401
+exclude = .git,.venv,__pycache__,docs,.github,build,dist,tests,benchmarks.py
\ No newline at end of file
diff --git a/scrapling/core/utils.py b/scrapling/core/utils.py
index 748020b..3cf887c 100644
--- a/scrapling/core/utils.py
+++ b/scrapling/core/utils.py
@@ -11,12 +11,12 @@ from lxml import html
html_forbidden = {html.HtmlComment, }
logging.basicConfig(
- level=logging.ERROR,
- format='%(asctime)s - %(levelname)s - %(message)s',
- handlers=[
- logging.StreamHandler()
- ]
- )
+ level=logging.ERROR,
+ format='%(asctime)s - %(levelname)s - %(message)s',
+ handlers=[
+ logging.StreamHandler()
+ ]
+)
def is_jsonable(content: Union[bytes, str]) -> bool:
@@ -94,7 +94,7 @@ class _StorageTools:
parent = element.getparent()
return tuple(
(element.tag,) if parent is None else (
- cls._get_element_path(parent) + (element.tag,)
+ cls._get_element_path(parent) + (element.tag,)
)
)
diff --git a/scrapling/engines/toolbelt/navigation.py b/scrapling/engines/toolbelt/navigation.py
index 363f233..faf4402 100644
--- a/scrapling/engines/toolbelt/navigation.py
+++ b/scrapling/engines/toolbelt/navigation.py
@@ -43,7 +43,7 @@ def construct_proxy_dict(proxy_string: Union[str, Dict[str, str]]) -> Union[Dict
}
except ValueError:
# Urllib will say that one of the parameters above can't be casted to the correct type like `int` for port etc...
- raise TypeError(f'The proxy argument\'s string is in invalid format!')
+ raise TypeError('The proxy argument\'s string is in invalid format!')
elif isinstance(proxy_string, dict):
valid_keys = ('server', 'username', 'password', )
diff --git a/setup.py b/setup.py
index 91aa89c..c360b7a 100644
--- a/setup.py
+++ b/setup.py
@@ -7,9 +7,9 @@ with open("README.md", "r", encoding="utf-8") as fh:
setup(
name="scrapling",
version="0.2.7",
- description="""Scrapling is a powerful, flexible, and high-performance web scraping library for Python. It
- simplifies the process of extracting data from websites, even when they undergo structural changes, and offers
- impressive speed improvements over many popular scraping tools.""",
+ description="""Scrapling is a powerful, flexible, and high-performance web scraping library for Python. It
+ simplifies the process of extracting data from websites, even when they undergo structural changes, and offers
+ impressive speed improvements over many popular scraping tools.""",
long_description=long_description,
long_description_content_type="text/markdown",
author="Karim Shoair",